© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9007
    Prev
    Next
    INDEX
    Explanations

    words related to visiting a city, especially San Francisco

    oai_token-act-pair · gemini-2.0-flash

    Travel and cities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.65
     typelib
    -0.60
     onResponse
    -0.59
    AddHtmlAttribute
    -0.57
     Entertainment
    -0.56
     Enjoy
    -0.55
    enumi
    -0.55
    Entertainment
    -0.54
    +:+
    -0.54
    SuppressLint
    -0.53
    POSITIVE LOGITS
    brainly
    0.74
    SourceChecksum
    0.67
     CanadaChoose
    0.59
     autorytatywna
    0.58
    transQ
    0.57
    expandindo
    0.56
    FOOTNOTES
    0.49
    Пусть
    0.49
     militaires
    0.49
    gendes
    0.48
    Activations Density 7.109%

    No Known Activations